© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13983
    Prev
    Next
    INDEX
    Explanations

    inconsistently formatted code and text fragments

    oai_token-act-pair · gemini-2.0-flash

    dashes/brackets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Билгалдахарш
    -0.59
     صوتيه
    -0.59
     propOrder
    -0.56
    o
    -0.56
     насељу
    -0.55
    ----</
    -0.54
    UrlResolution
    -0.53
     getItemId
    -0.53
    aarrggbb
    -0.53
    ORY
    -0.53
    POSITIVE LOGITS
    ta
    0.76
    ty
    0.71
    tes
    0.70
    to
    0.69
    tas
    0.63
    ts
    0.63
    te
    0.62
    ed
    0.62
    ten
    0.60
    tn
    0.60
    Activations Density 12.076%

    No Known Activations